Wikipedia is a critical source of information for millions of users across the Web. It serves as a key resource for large language models, search engines, question-answering systems, and other Web-based applications. In Wikipedia, content needs to be verifiable, meaning that readers can check that claims are backed by references to reliable sources. This depends on manual verification by editors, an effective but labor-intensive process, especially given the high volume of daily edits. To address this challenge, we introduce a multilingual machine learning system to assist editors in identifying claims requiring citations. Our approach is tested in 10 language editions of Wikipedia, outperforming existing benchmarks for reference need assessment. We not only consider machine learning evaluation metrics but also system requirements, allowing us to explore the trade-offs between model accuracy and computational efficiency under real-world infrastructure constraints. We deploy our system in production and release data and code to support further research.

Wikipedia is powered by MediaWiki, a free and open-source software that is also the infrastructure for many other wiki-based online encyclopedias. These include the recently launched website Ruwiki, which has copied and modified the original Russian Wikipedia content to conform to Russian law. To identify practices and narratives that could be associated with different forms of knowledge manipulation, this article presents an in-depth analysis of this Russian Wikipedia fork. We propose a methodology to characterize the main changes with respect to the original version. The foundation of this study is a comprehensive comparative analysis of more than 1.9M articles from Russian Wikipedia and its fork. Using meta-information and geographical, temporal, categorical, and textual features, we explore the changes made by Ruwiki editors. Furthermore, we present a classification of the main topics of knowledge manipulation in this fork, including a numerical estimation of their scope. This research not only sheds light on significant changes within Ruwiki, but also provides a methodology that could be applied to analyze other Wikipedia forks and similar collaborative projects.

Wikipedia is the largest web repository of free knowledge. Volunteer editors devote time and effort to creating and expanding articles in more than 300 language editions. As content quality varies from article to article, editors also spend substantial time rating articles with specific criteria. However, keeping these assessments complete and up-to-date is largely impossible given the ever-changing nature of Wikipedia. To overcome this limitation, we propose a novel computational framework for modeling the quality of Wikipedia articles. State-of-the-art approaches to model Wikipedia article quality have leveraged machine learning techniques with language-specific features. In contrast, our framework is based on language-agnostic structural features extracted from the articles, a set of universal weights, and a language version-specific normalization criterion. Therefore, we ensure that all language editions of Wikipedia can benefit from our framework, even those that do not have their own quality assessment scheme. Using this framework, we have built datasets with the feature values and quality scores of all revisions of all articles in the existing language versions of Wikipedia. We provide a descriptive analysis of these resources and a benchmark of our framework. In addition, we discuss possible downstream tasks to be addressed with these datasets, which are released for public use.

Information presented in Wikipedia articles must be attributable to reliable published sources in the form of references. This study examines over 5 million Wikipedia articles to assess the reliability of references in multiple language editions. We quantify the cross-lingual patterns of the perennial sources list, a collection of reliability labels for web domains identified and collaboratively agreed upon by Wikipedia editors. We discover that some sources (or web domains) deemed untrustworthy in one language (i.e., English) continue to appear in articles in other languages. This trend is especially evident with sources tailored for smaller communities. Furthermore, non-authoritative sources found in the English version of a page tend to persist in other language versions of that page. We finally present a case study on the Chinese, Russian, and Swedish Wikipedias to demonstrate a discrepancy in reference reliability across cultures. Our finding highlights future challenges in coordinating global knowledge on source reliability.

This paper presents a novel design of the system aimed at supporting the Wikipedia community in addressing vandalism on the platform. To achieve this, we collected a massive dataset of 47 languages, and applied advanced filtering and feature engineering techniques, including multilingual masked language modeling to build the training dataset from human-generated data. The performance of the system was evaluated through comparison with the one used in production in Wikipedia, known as ORES. Our research results in a significant increase in the number of languages covered, making Wikipedia patrolling more efficient to a wider range of communities. Furthermore, our model outperforms ORES, ensuring that the results provided are not only more accurate but also less biased against certain groups of contributors.

Wikipedia plays a crucial role in the integrity of the Web. This work analyzes the reliability of this global encyclopedia through the lens of its references. We operationalize the notion of reference quality by defining reference need (RN), i.e., the percentage of sentences missing a citation, and reference risk (RR), i.e., the proportion of non-authoritative references. We release Citation Detective, a tool for automatically calculating the RN score, and discover that the RN score has dropped by 20 percent point in the last decade, with more than half of verifiable statements now accompanying references. The RR score has remained below 1% over the years as a result of the efforts of the community to eliminate unreliable references. We propose pairing novice and experienced editors on the same Wikipedia article as a strategy to enhance reference quality. Our quasi-experiment indicates that such a co-editing experience can result in a lasting advantage in identifying unreliable sources in future edits. As Wikipedia is frequently used as the ground truth for numerous Web applications, our findings and suggestions on its reliability can have a far-reaching impact. We discuss the possibility of other Web services adopting Wiki-style user collaboration to eliminate unreliable content.

Sections are the building blocks of Wikipedia articles. They are used by editors to create a structure for the content of articles, which in turn improves reading and editing workflows. Today, millions of carefully curated section titles exist in more than 160 actively edited Wikipedia languages as standalone components of a larger system. Understanding the connection and correspondence of section titles across languages presents various application opportunities such as article template recommendation, i.e., given a source language article, we can generate a skeleton of section titles for a target language. Inspired by this real-world data mining problem, the present paper introduces the problem of aligning section titles across Wikipedia languages and proposes a probabilistic method for identifying such correspondences. Instead of applying translation tools to section titles (which may generate out-of lexicon titles), we develop a supervised model that identifies cross-language mappings based on section content features. We collected a ground-truth dataset created for this purpose with the help of volunteers. In addition, we use Probabilistic Soft Logic to model the dependencies between multilingual section pairings. We show that our approach performs better than machine translation solutions in about 80% of the language pairs, including distant language mappings such as Arabic to Russian or French to Japanese and in many of the more closely related languages such as French to Spanish.

While Wikipedia has been utilized for fact-checking and claim verification to debunk misinformation and disinformation, it is essential to either improve article quality and rule out noisy articles. Self-contradiction is one of the low-quality article types in Wikipedia. In this work, we propose a task of detecting self-contradiction articles in Wikipedia. Based on the "self-contradictory" template, we create a novel dataset for the self-contradiction detection task. Conventional contradiction detection focuses on comparing pairs of sentences or claims, but self-contradiction detection needs to further reason the semantics of an article and simultaneously learn the contradiction-aware comparison from all pairs of sentences. Therefore, we present the first model, Pairwise Contradiction Neural Network (PCNN), to not only effectively identify self-contradiction articles, but also highlight the most contradiction pairs of contradiction sentences. The main idea of PCNN is two-fold. First, to mitigate the effect of data scarcity on self-contradiction articles, we pre-train the module of pairwise contradiction learning using SNLI and MNLI benchmarks. Second, we select top-K sentence pairs with the highest contradiction probability values and model their correlation to determine whether the corresponding article belongs to self-contradiction. Experiments conducted on the proposed WikiContradiction dataset exhibit that PCNN can generate promising performance and comprehensively highlight the sentence pairs the contradiction locates.

With the growth of fake news and disinformation, the NLP community has been working to assist humans in fact-checking. However, most academic research has focused on model accuracy without paying attention to resource efficiency, which is crucial in real-life scenarios. In this work, we review the State-of-the-Art datasets and solutions for Automatic Fact-checking and test their applicability in production environments. We discover overfitting issues in those models, and we propose a data filtering method that improves the model's performance and generalization. Then, we design an unsupervised fine-tuning of the Masked Language models to improve its accuracy working with Wikipedia. We also propose a novel query enhancing method to improve evidence discovery using the Wikipedia Search API. Finally, we present a new fact-checking system, the WikiCheck API that automatically performs a facts validation process based on the Wikipedia knowledge base. It is comparable to SOTA solutions in terms of accuracy and can be used on low-memory CPU instances.

Wikipedia is the largest online encyclopedia, used by algorithms and web users as a central hub of reliable information on the web.The quality and reliability of Wikipedia content is maintained by a community of volunteer editors. Machine learning and information retrieval algorithms could help scale up editors' manual efforts around Wikipedia content reliability. However, there is a lack of large-scale data to support the development of such research. To fill this gap, in this paper, we propose Wiki-Reliability, the first dataset of English Wikipedia articles annotated with a wide set of content reliability issues. To build this dataset, we rely on Wikipedia "templates". Templates are tags used by expert Wikipedia editors to indicate content issues, such as the presence of "non-neutral point of view" or "contradictory articles", and serve as a strong signal for detecting reliability issues in a revision. We select the 10 most popular reliability-related templates on Wikipedia, and propose an effective method to label almost 1M samples of Wikipedia article revisions as positive or negative with respect to each template. Each positive/negative example in the dataset comes with the full article text and 20 features from the revision's metadata. We provide an overview of the possible downstream tasks enabled by such data, and show that Wiki-Reliability can be used to train large-scale models for content reliability prediction. We release all data and code for public use.

As one of the Web's primary multilingual knowledge sources, Wikipedia is read by millions of people across the globe every day. Despite this global readership, little is known about why users read Wikipedia's various language editions. To bridge this gap, we conduct a comparative study by combining a large-scale survey of Wikipedia readers across 14 language editions with a log-based analysis of user activity. We proceed in three steps. First, we analyze the survey results to compare the prevalence of Wikipedia use cases across languages, discovering commonalities, but also substantial differences, among Wikipedia languages with respect to their usage. Second, we match survey responses to the respondents' traces in Wikipedia's server logs to characterize behavioral patterns associated with specific use cases, finding that distinctive patterns consistently mark certain use cases across language editions. Third, we show that certain Wikipedia use cases are more common in countries with certain socio-economic characteristics; e.g., in-depth reading of Wikipedia articles is substantially more common in countries with a low Human Development Index. These findings advance our understanding of reader motivations and behaviors across Wikipedia languages and have implications for Wikipedia editors and developers of Wikipedia and other Web technologies.

Topic discovery and evolution (TDE) has been a problem which has gained long standing interest in the research community. The goal in topic discovery is to identify groups of keywords from large corpora so that the information in those corpora are summarized succinctly. The nature of text corpora has changed dramatically in the past few years with the advent of social media. Social media services allow users to constantly share, follow and comment on posts from other users. Hence, such services have given a new dimension to the traditional text corpus. The new dimension being that today's corpora have a social context embedded in them in terms of the community of users interested in a particular post, their profiles etc. We wish to harness this social context that comes along with the textual content for TDE. In particular, our goal is to both qualitatively and quantitatively analyze when social context actually helps with TDE. Methodologically, we approach the problem of TDE by a proposing non-negative matrix factorization (NMF) based model that incorporates both the textual information and social context information. We perform experiments on large scale real world dataset of news articles, and use Twitter as the platform providing information about the social context of these news articles. We compare with and outperform several state-of-the-art baselines. Our conclusion is that using the social context information is most useful when faced with topics that are particularly difficult to detect.

We examine biases in online news sources and social media communities around them. To that end, we introduce unsupervised methods considering three types of biases: selection or ``gatekeeping'' bias, coverage bias, and statement bias, characterizing each one through a series of metrics. Our results, obtained by analyzing 80 international news sources during a two-week period, show that biases are subtle but observable, and follow geographical boundaries more closely than political ones. We also demonstrate how these biases are to some extent amplified by social media.

Influential people have an important role in the process of information diffusion. However, there are several ways to be influential, for example, to be the most popular or the first that adopts a new idea. In this paper we present a methodology to find trendsetters in information networks according to a specific topic of interest. Trendsetters are people that adopt and spread new ideas influencing other people before these ideas become popular. At the same time, not all early adopters are trendsetters because only few of them have the ability of propagating their ideas by their social contacts through word-of-mouth. Differently from other influence measures, a trendsetter is not necessarily popular or famous, but the one whose ideas spread over the graph successfully. Other metrics such as node in-degree or even standard Pagerank focus only in the static topology of the network. We propose a ranking strategy that focuses on the ability of some users to push new ideas that will be successful in the future. To that end, we combine temporal attributes of nodes and edges of the network with a Pagerank based algorithm to find the trendsetters for a given topic. To test our algorithm we conduct innovative experiments over a large Twitter dataset. We show that nodes with high in-degree tend to arrive late for new trends, while users in the top of our ranking tend to be early adopters that also influence their social contacts to adopt the new trend.

Social-networking sites have started to offer tools that suggest "guests" who should be invited to user-defined social events (e.g., birthday parties, networking events). The problem of how to recommend people to events is similar to the more traditional (recommender system) problem of how to recommend events (items) to people (users). Yet, upon Foursquare data of "who visits what" in the city of London, we show that a state-of-the-art recommender system does not perform well -mainly because of data sparsity. To fix this problem, we add domain knowledge to the recommendation process. From the complex system literature in human mobility, we learn two insights: 1) there are special individuals (often called power users) who visit many places; and 2) individuals go to a venue not only because they like it but also because they are close-by. We model these insights into two simple models and learn that: 1) simply recommending power users works better than random but is far from producing the best recommendations; 2) an item-based recommender system produces accurate recommendations; and 3) recommending places that are closest to a user's geographic center of interest produces recommendations that are as accurate as, if not more accurate than, item-based recommender's. This last result has practical implications as it offers guidelines for designing location-based recommender systems and for partly addressing cold-start situations.